Lijin Wu
Lijin Wu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Feilong Liao
Fujian Power Co., Ltd. Electric Power Research Institute
3 shared publicationsHao Song
Zhejiang University of Technology
2 shared publicationsJiajun Zhou
Zhejiang University of Technology
2 shared publicationsJianye Huang
Fujian Power Co., Ltd., Electric Power Research Institute
2 shared publicationsJindong He
Fujian Power Co., Ltd., Electric Power Research Institute
2 shared publicationsNan Lin
Fujian Power Co., Ltd., Electric Power Research Institute
2 shared publications
Latest Publications
- 1 August 2024
- Published by Springer Nature
- p. 253-265
Modeling the BGP Prefix Hijack via Pollution and Recovery Processes
- 1 August 2024
- Published by Springer Nature
- p. 253-265
Modeling the BGP Prefix Hijack via Pollution and Recovery Processes
- 1 August 2024
- Published by Springer Nature
- p. 19-34
EG-ConMix: An Intrusion Detection Method Based on Graph Contrastive Learning
- 1 August 2024
- Published by Springer Nature
- p. 19-34
EG-ConMix: An Intrusion Detection Method Based on Graph Contrastive Learning
- 1 August 2024
- Published by Springer Nature
- p. 412-430
Improving the Adversarial Transferability of Radio Signal with Denoising, Data Diversity, and Gradient Average
- 1 August 2024
- Published by Springer Nature
- p. 412-430
Improving the Adversarial Transferability of Radio Signal with Denoising, Data Diversity, and Gradient Average
- 1 August 2024
- Published by Springer Nature
- p. 237-252
Incremental Network Traffic Category Models Based on Hybrid Learning Strategies
- 1 August 2024
- Published by Springer Nature
- p. 237-252
Incremental Network Traffic Category Models Based on Hybrid Learning Strategies
- Open Access
EG-ConMix: An Intrusion Detection Method based on Graph Contrastive Learning
As the number of IoT devices increases, security concerns become more prominent. The impact of threats can be minimized by deploying Network Intrusion Detection System (NIDS) by monitoring network traffic, detecting and discovering intrusions, and issuing security alerts promptly. Most intrusion detection research in recent years has been directed towards the pair of traffic itself without considering the interrelationships among them, thus limiting the monitoring of complex IoT network attack events. Besides, anomalous traffic in real networks accounts for only a small fraction, which leads to a severe imbalance problem in the dataset that makes algorithmic learning and prediction extremely difficult. In this paper, we propose an EG-ConMix method based on E-GraphSAGE, incorporating a data augmentation module to fix the problem of data imbalance. In addition, we incorporate contrastive learning to discern the difference between normal and malicious traffic samples, facilitating the extraction of key features. Extensive experiments on two publicly available datasets demonstrate the superior intrusion detection performance of EG-ConMix compared to state-of-the-art methods. Remarkably, it exhibits significant advantages in terms of training speed and accuracy for large-scale graphs.
Open AccessEG-ConMix: An Intrusion Detection Method based on Graph Contrastive Learning
As the number of IoT devices increases, security concerns become more prominent. The impact of threats can be minimized by deploying Network Intrusion Detection System (NIDS) by monitoring network traffic, detecting and discovering intrusions, and issuing security alerts promptly. Most intrusion detection research in recent years has been directed towards the pair of traffic itself without considering the interrelationships among them, thus limiting the monitoring of complex IoT network attack events. Besides, anomalous traffic in real networks accounts for only a small fraction, which leads to a severe imbalance problem in the dataset that makes algorithmic learning and prediction extremely difficult. In this paper, we propose an EG-ConMix method based on E-GraphSAGE, incorporating a data augmentation module to fix the problem of data imbalance. In addition, we incorporate contrastive learning to discern the difference between normal and malicious traffic samples, facilitating the extraction of key features. Extensive experiments on two publicly available datasets demonstrate the superior intrusion detection performance of EG-ConMix compared to state-of-the-art methods. Remarkably, it exhibits significant advantages in terms of training speed and accuracy for large-scale graphs.